Multi Agent

This skill provides a conceptual framework for progressively refining context retrieval in multi-agent workflows. It describes a 4-phase DISPATCH-EVALUATE-REFINE-LOOP pattern to solve the 'subagent context problem' where agents don't know what context they need until they start working.

Claude Flow is an enterprise-grade AI agent orchestration plugin providing 150+ commands, 74+ specialized agents, and swarm coordination capabilities. It enables multi-agent workflows with SPARC methodology, GitHub automation, neural training, and cross-session memory persistence through MCP server integration.

A comprehensive collection of educational skills for learning context engineering principles. Covers context window management, multi-agent coordination patterns, memory system design, tool creation, and evaluation frameworks. All scripts are demonstrations using mock data to illustrate concepts without external dependencies.

MCP Agent Mail enables multiple AI coding agents to coordinate asynchronously through a mail-like system. It provides inbox/outbox messaging, file reservations to prevent conflicts, and contact management, with all communications stored in Git for human auditability.

A comprehensive reference guide for the Langroid multi-agent LLM framework. Provides design patterns and code examples for agent configuration, stateful tool handlers, task control with done_sequences, batch processing, MCP tool integration, and quiet mode output control.

This skill provides instructions for using the tmux-cli command to communicate with other CLI agents or scripts running in different tmux panes. It enables executing commands in specific panes with exit code detection, useful for multi-step automation and agent coordination. Requires separate installation of the claude-code-tools package.

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Loki Mode is a comprehensive autonomous agent orchestration system for Claude Code that automates the full software development lifecycle. It features 37+ specialized agent types, multi-tier model selection (Opus/Sonnet/Haiku), parallel execution via git worktrees, and extensive quality gates to ensure high-quality autonomous development.

A comprehensive guide for building autonomous AI agents using Pydantic AI (Python) and Claude Agent SDK (Node.js). Covers agent architecture, tool design, multi-agent coordination, memory management, guardrails, and testing patterns with practical code examples.

A comprehensive reference guide for understanding and optimizing context in LLM agent systems. Covers context anatomy, degradation patterns, multi-agent verification workflows, and optimization techniques like compaction and observation masking.

A comprehensive reference guide for designing multi-agent architectures in Claude Code. It covers three main patterns (supervisor/orchestrator, peer-to-peer/swarm, and hierarchical), along with context isolation strategies, consensus mechanisms, failure mode mitigations, and memory system designs ranging from simple file-based to temporal knowledge graphs.

Coordinate multi-agent code review with specialized perspectives. Use when conducting code reviews, analyzing PRs, evaluating staged changes, or reviewing specific files. Handles security, performance, quality, and test coverage analysis with confidence scoring and actionable recommendations.